Topic-Aware Sensitive Information Detection in Chinese Large Language Model

With the rapid advancement of deep learning, generative AI models have emerged as a prominent area of focus. However, these developments bring potential security concerns. China’s guiding document of government on generative AI security identifies 31 specific security risks across five categories, including content that violates socialist core values and discriminatory content. Detecting the sensitivity of both user input and model-generated content has therefore become a critical challenge for the security of generative AI models. This paper proposes a robust scheme for detecting sensitive information in the Chinese languages generated from the large language models. Initially, we detect and classify the security risks outlined in the document "Basic Security Requirements for Generative Artificial Intelligence Service" and develop a comprehensive dataset, named Chinese Sensitive Language Detection (CSLD). Specifically, in order to leverage the semantics of languages, we introduce the topic model to pre-analyze text data and construct topic-augmented classification vectors (TACV) that supply effective contextual information for sensitive content detection. Additionally, we propose a topic-infused attention mechanism (TIAM) to provide richer contextual information and relevant topics to guide sensitive information detection. At the same time, the proposed framework is designed to integrate with various classes of Chinese pre-trained models, enabling accurate classification of sensitive content while maintaining low latency and memory usage. Furthermore, the proposed dataset surpasses existing ones in terms of coverage, data volume, and its focus on the security challenges specific to Chinese large language models. Without bells and whistles, our experiments demonstrate that our model outperforms existing models in terms of accuracy and efficiency on the CSLD dataset.